© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 2849
    Prev
    Next
    INDEX
    Explanations

    foreign words and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    als
    1.75
    ised
    1.64
    Listener
    1.57
    gameOver
    1.55
    u
    1.53
    setLayout
    1.52
    Gravestone
    1.48
     vitamins
    1.47
    grant
    1.41
     anxious
    1.41
    POSITIVE LOGITS
    یه
    2.21
    ী
    2.11
    ्ज
    2.06
     Dette
    2.03
     resellers
    2.02
    곳
    2.01
    ƌ
    1.99
    ా
    1.98
    רי
    1.95
     이는
    1.92
    Activations Density 0.000%

    No Known Activations